Update README.md

README.md

@@ -4,58 +4,111 @@ library_name: diffusers
 license: openrail++
 tags:
 - text-to-image
-- text-to-image
 - diffusers-training
 - diffusers
 - lora
 - template:sd-lora
-- stable-diffusion-xl
-- stable-diffusion-xl-diffusers
+- stable-diffusion-3
+- stable-diffusion-3-diffusers
 instance_prompt: <leaf microstructure>
 widget: []
 ---
 
-<!-- This model card has been generated automatically according to the information the training script had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-
-# SDXL LoRA DreamBooth - lamm-mit/leaf_LoRA_SD3_V12
+# Stable Diffusion 3 Medium Fine-tuned with Leaf Images
 
 <Gallery />
 
 ## Model description
 
-These are lamm-mit/leaf_LoRA_SD3_V12 LoRA adaption weights for stabilityai/stable-diffusion-3-medium-diffusers.
-
-The weights were trained using [DreamBooth](https://dreambooth.github.io/).
+These are LoRA adaption weights for stabilityai/stable-diffusion-3-medium-diffusers.
 
-LoRA for the text encoder was enabled: False.
+## Trigger words
 
-Special VAE used for training: None.
+The following image were used during fine-tuning using the keyword <leaf microstructure>:
 
-## Trigger words
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/623ce1c6b66fedf374859fe7/sI_exTnLy6AtOFDX1-7eq.png)
 
 You should use <leaf microstructure> to trigger the image generation.
 
-## Download model
+#### How to use
+
+Defining some helper functions:
 
-Weights for this model are available in Safetensors format.
+```python
+from diffusers import DiffusionPipeline
+import torch
+import os
+from datetime import datetime
+from PIL import Image
+
+def generate_filename(base_name, extension=".png"):
+    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+    return f"{base_name}_{timestamp}{extension}"
+
+def save_image(image, directory, base_name="image_grid"):
+    
+    filename = generate_filename(base_name)
+    file_path = os.path.join(directory, filename)
+    image.save(file_path)
+    print(f"Image saved as {file_path}")
+
+def image_grid(imgs, rows, cols, save=True, save_dir='generated_images', base_name="image_grid",
+              save_individual_files=False):
+    
+    if not os.path.exists(save_dir):
+        os.makedirs(save_dir)
+        
+    assert len(imgs) == rows * cols
+
+    w, h = imgs[0].size
+    grid = Image.new('RGB', size=(cols * w, rows * h))
+    grid_w, grid_h = grid.size
+
+    for i, img in enumerate(imgs):
+        grid.paste(img, box=(i % cols * w, i // cols * h))
+        if save_individual_files:
+            save_image(img, save_dir, base_name=base_name+f'_{i}-of-{len(imgs)}_')
+            
+    if save and save_dir:
+        save_image(grid, save_dir, base_name)
+    
+    return grid
+```
 
-[Download](lamm-mit/leaf_LoRA_SD3_V12/tree/main) them in the Files & versions tab.
+Model loading and generation pipeline:
 
+```python
 
-## Intended uses & limitations
+repo_id_load='lamm-mit/stable-diffusion-3-medium-leaf-inspired'
 
-#### How to use
+pipeline = DiffusionPipeline.from_pretrained ("stabilityai/stable-diffusion-3-medium-diffusers", 
+                                              torch_dtype=torch.float16
+                                             )
 
-```python
-# TODO: add an example code snippet for running this diffusion pipeline
-```
+pipeline.load_lora_weights(repo_id_load)
+pipeline=pipeline.to('cuda')
 
-#### Limitations and bias
+prompt          = "a cube in the shape of a <leaf microstructure>" 
+negative_prompt = ""
 
-[TODO: provide examples of latent issues and potential remediations]
+num_samples = 3
+num_rows = 3
+n_steps=75
+guidance_scale=15
+all_images = []
 
-## Training details
+for _ in range(num_rows):
+    image = pipeline(prompt,num_inference_steps=n_steps,num_images_per_prompt=num_samples,
+                     guidance_scale=guidance_scale,negative_prompt=negative_prompt).images
+     
+    all_images.extend(image)
+
+grid = image_grid(all_images, num_rows, num_samples,  
+                  save_individual_files=True, 
+                  save_dir='generated_images', 
+                  base_name="image_grid",
+                 )
+grid
+```
 
-[TODO: describe the data used to train the model]
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/623ce1c6b66fedf374859fe7/qk5kRJJmetvhZ0ctltc3z.png)